Modern deep neural networks, particularly recent large language models, come with
massive model sizes that require significant computational and storage resources. To …

Previous works utilized" smaller-norm-less-important" criterion to prune filters with smaller
norm values in a convolutional neural network. In this paper, we analyze this norm-based …

Data redundancy is ubiquitous in the inputs and intermediate results of Deep Neural
Networks (DNN). It offers many significant opportunities for improving DNN performance and …

Filter pruning has been widely applied to neural network compression and acceleration.
Existing methods usually utilize pre-defined pruning criteria, such as Lp-norm, to prune …

In this paper, we strive to answer the question'how to collaboratively learn convolutional
neural network (CNN)-based and vision transformer (ViT)-based models by selecting and …

In this work, we introduce an extension to ProtoPNet called ProtoPShare which shares
prototypical parts between classes. To obtain prototype sharing we prune prototypical parts …

During the past decade, human activity recognition (HAR) using wearable sensors has
become a new research hot spot due to its extensive use in various application domains …

We present a filter correlation based model compression approach for deep convolutional
neural networks. Our approach iteratively identifies pairs of filters with the largest pairwise …

The existence of redundancy in convolutional neural networks (CNNs) enables us to remove
some filters/channels with acceptable performance drops. However, the training objective of …

It is of great significance to compress neural network models so that they can be deployed
on resource-constrained embedded mobile devices. However, due to the lack of theoretical …